marnixkoops

"""
# [+] PROJECT INFO
#     - Cox Proportional Hazard Regression model (Survival Analysis)
#     - Main purpose is to predict post-session conversion likelihood on customer level (cookie_id)
#
# Owner: Marnix Koops / marnixkoops@gmail.com
"""

# ==================================================================================================
# [+] SETUP

marnixkoops

df = pd.concat(
    [
        pd.read_csv(f)
        for f in glob.glob("./folder/*.csv")
    ],
    ignore_index=True,
)

marnixkoops

import logging

logging.basicConfig(  # logging to terminal & disk file
    level=logging.INFO,
    format="%(asctime)s [%(threadName)s] [%(levelname)s]  %(message)s",
    handlers=[logging.FileHandler("logfile.log"), logging.StreamHandler()],
)
logger = logging.getLogger()

marnixkoops

import numpy as np
import pandas as pd
import time
import datetime
import warnings
import gc

import tensorflow as tf
from tensorflow import keras
from tensorflow.python.client import device_lib

marnixkoops

def downcast_datatypes(df):
    float_cols = df.select_dtypes(include=['float'])
    int_cols = df.select_dtypes(include=['int'])

    for cols in float_cols.columns:
        df[cols] = pd.to_numeric(df[cols], downcast='float')
    for cols in int_cols.columns:
        df[cols] = pd.to_numeric(df[cols], downcast='integer')

    return df

marnixkoops

# %% markdown
# WEER IMPACT

# %%
# SETUP
import pandas as pd
import numpy as np
import pickle
import matplotlib
import matplotlib.pyplot as plt

marnixkoops

import pandas as pd
import numpy as np

from custom_code import timefold
from sklearn import preprocessing


def target_encoder(df, column, target, index=None, method='mean'):
    """
    Target-based encoding is numerization of a categorical variables via the target variable. Main purpose is to deal

marnixkoops

    # Group by product / timewindow and compute aggregate features
    print('[+] Generating weekly lagged product aggregation features ...')
    agg_week = demand_df.groupby(['product_id', 'year', 'weekofyear'])[
        'actual_raw'].agg(num_week_lag_aggregations)
    agg_week.columns = ["_week_lagged_".join(agg_feature)
                        for agg_feature in agg_week.columns.ravel()]
    agg_week.reset_index(drop=False, inplace=True)

    print('[+] Generating monthly lagged product aggregation features ...')
    agg_month = demand_df.groupby(['product_id', 'year', 'month'])[

marnixkoops

############################################################################################
#                                                                                  [+] SETUP
############################################################################################

import numpy as np
import pandas as pd
import gc
import glob
import os

marnixkoops

# DARK
jt -t onedork -f sourcemed -fs 10 -altp -tfs 11 -nfs 115 -cellw 80% -T

# LIGHT
jt -t grade3 -f sourcemed -fs 10 -altp -tfs 11 -nfs 115 -cellw 80% -T